© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 131056
    Prev
    Next
    INDEX
    Explanations

    my question or problem arises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SEMESTER
    -1.12
    chieben
    -1.12
     MINUTE
    -1.10
     poffe
    -1.09
     چیه
    -1.06
     difp
    -1.05
     fhort
    -1.05
    辈子
    -1.05
     fufficient
    -1.04
     neceffary
    -1.01
    POSITIVE LOGITS
     another
    1.88
     why
    1.28
     our
    1.27
    อีก
    1.24
     point
    1.23
    Another
    1.19
     how
    1.17
     question
    1.12
     again
    1.09
     the
    1.07
    Activations Density 0.008%

    No Known Activations